Will the Write-Ahead-Log become the bottleneck of Cassandra?

user_6438341 0
Viewed 123

In a Cassandra database, a write needs to be logged in the Write Ahead Log first and then added to the memtable in memory. Since the Write Ahead Log is on disk, although it performs sequential writes（i.e., append only）, will it still be much slower than memory access, thus become the performance bottleneck for the writes？

If I understand it correctly, Cassandra supports the mechanism to store the Write Ahead Log in OS cache, and then flush it to disk every pre-configured amount of time(say 10 seconds). However, does it mean the data changes made within this 10 seconds could be all lost if the machine crashes?

cassandra
1 Answers

You can control if the sync of commit log using the commitlog-sync configuration. By default it's periodic, and synced to disk every 10 seconds (controlled by commitlog_sync_period_in_ms setting).

And yes, if you lose the power there is a risk that data in the commit log is lost. But Cassandra relies on the fact that you have multiple replicas, and if you did setup correctly, each replica should be in separate rack (at least, better if you have additional data centers) with separate power, etc.

Alex_Ott_186270
Related